vix.ing · top · new · best · stats · spec

Jerome Wynne

  1. AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
    2024/10/11 by Maksym Andriushchenko, Alexandra Souly, Andriushchenko, Maksym +25 · 102 citations
    Computer Science · #Blockchain Technology Applications and Security
  2. Quantifying Frontier LLM Capabilities for Container Sandbox Escape
    2026/03/01 by Rahul Marchand, Art O Cathain, Jerome Wynne +8 · 4 voices · 1 citation
    Computer Science · #cs.AI #cs.CR